Fast Bayesian people detection
Gwenn Englebienne, Ben Kröse · UvA-DARE (University of Amsterdam) · 2010
Template-based methods have been shown to be effective at solving the problem of tracking specific objects, but their large number of free parameters can make them slow to apply and hard to optimise globally. In this work, we propose a template-based method for tracking people with fixed cameras, which automatically detects the number of people in a frame, is robust to occlusions, and can run at near-real-time frame rates. We demonstrate the effectiveness of the method by comparing it to a state-of-the-art background segmentation algorithm and show its important performance advantage.